© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10708
    Prev
    Next
    INDEX
    Explanations

    energy and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulis
    -0.08
     ÏĦÏį
    -0.08
    acula
    -0.08
    Ñģок
    -0.07
     sizing
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    ãģªãģĹ
    -0.07
    管çĶ¨
    -0.07
    çļĦåĬĽåº¦
    -0.07
    æĶĺ
    -0.07
    POSITIVE LOGITS
    æĶ¶äºİ
    0.07
    สà¸ĸาà¸Ļะ
    0.07
    éĺ±
    0.07
    èĥ½éĩı
    0.06
     lowered
    0.06
     inaccessible
    0.06
     accessed
    0.06
    ä½įç½®
    0.06
    çĬ¶æĢģ
    0.06
    liness
    0.06
    Activations Density 0.007%

    No Known Activations